SicariusSicariiStuff
/

Negative_LLAMA_70B_EXL3_d_2.5bpw

Model card Files Files and versions Community

Note

This was made to test extremely low quants. 70B is pretty usable at 2.50 bpw. A custom strategy for quanting was used, for details check EXL3 repo. This was made to fit a single 24GB card.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SicariusSicariiStuff/Negative_LLAMA_70B_EXL3_d_2.5bpw

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Finetuned

SicariusSicariiStuff/Negative_LLAMA_70B

Finetuned

(12)

this model

Dataset used to train SicariusSicariiStuff/Negative_LLAMA_70B_EXL3_d_2.5bpw